Integrating machine learning and molecular docking to reveal the molecular network of aflatoxin B1-induced colorectal cancer

Aflatoxin B1 (AFB1) contributes to colorectal cancer development through multiple molecular pathways. This study aims to investigate the molecular mechanisms underlying Colorectal cancer (CRC) induced by AFB1. Using integrative transcriptomic differential expression data, we enumerated candidate genes for AFB1-related colorectal cancer based on the list of published AFB1 protein targets. The molecular relationship between AFB1 and its candidates were verified by machine learning, network-based toxicology and molecular docking algorithms. The study screened 55 AFB1-related CRC genes. Through machine learning algorithm, three key genes, ABCG2, PDE3A and CCND1, were selected. Down-regulation of ABCG2 and PDE3A but upregulation of CCND1 were observed under expression (P < 0.05). Molecular docking demonstrated that the binding was stable between AFB1 and target proteins. Our analysis determines three key regulatory genes that play a key role in the colorectal cancer induction induced by AFB1. We show that AFB1 directly interacts with the transcripts of these genes, their protein products and disturbs the network function. This study demonstrates that AFB1 may promote CRC pathogenesis by targeting specific genes and signaling pathways. Machine learning identified three core regulatory genes, and molecular docking confirmed AFB1’s high binding affinity with key targets. These findings provide critical insights for further mechanistic exploration of AFB1-induced colorectal cancer.